join_set2 = np.genfromtxt('./data/BookCrossing/MLFK2.csv',
skip_header=True,
dtype=int)
r2 = mmread('./data/BookCrossing/MLR2Sparse.txt', )
Y = np.matrix(np.genfromtxt('./data/BookCrossing/MLY.csv', skip_header=True)).T
k = [join_set1 - 1, join_set2 - 1]
T = hstack((r1.tocsr()[k[0]], r2.tocsr()[k[1]]))
w_init = np.matrix(np.random.randn(T.shape[1], 1))
gamma = 0.000001
iterations = 20
result_eps = 1e-6
print "start factorized matrix"
normalized_matrix = nm.NormalizedMatrix(s, [r1, r2], k)
print "end factorized matrix"
import time
m_regressor = NormalizedLinearRegression()
print "start materialized regression"
start = time.time()
m_regressor.fit(T, Y, w_init=w_init)
end = time.time()
print "end materialized regression"
m_time = end - start
w_init = np.matrix(np.random.randn(T.shape[1], 1))
print "start factorized regression"
n_regressor = NormalizedLinearRegression()
# Scalar
print "start tesing scalar"
total = []
for f in range(1, 5):
result = []
for t in range(1, 21):
print "scalar, feature ratio:", f, "tuple ratio", t
dr = ds * f
ns = nr * t
s = np.random.rand(ns, ds)
r = [np.random.rand(nr, dr)]
num = np.random.randint(nr, size=ns)
k = [num]
T = np.hstack((s, r[0][k[0]]))
normalized_matrix = nm.NormalizedMatrix(s, r, k)
avg = []
for _ in range(trails):
m_start = time.time()
# np.add(T, 5)
np.power(T, 2)
m_end = time.time()
n_start = time.time()
# normalized_matrix + 5
np.power(normalized_matrix, 2)
n_end = time.time()
avg.append((m_end - m_start) / (n_end - n_start))
